AI that understands your business.

Your company's answers are buried across the systems you use every day. MerchantsBI brings that information together, gives AI the context to understand it, and puts the answers at your fingertips.

How it works

See the difference, step by step.

Compare
Look
Stage bar

01ConnectConnect every system once, not once per AI tool.

01ConnectConnect every system once, not once per AI tool.

Five systems, five builds

Each system needs its own MCP server: sign-in, rate limits, field mapping and hosting. When one system changes, that piece breaks and someone on your team fixes it.

Doing it yourself

One MCP server per system, built and kept running by you

pieces to build0
separate tools for the AI0
Connected once, in one place

Pick your systems from 56 connectors. MerchantsBI handles sign-in, limits and fields, and brings everything into one model the AI reads.

With

Connect each system once. Everything lands in one model

sources connected0
places the AI reads0

02SelectOnly the columns that hold data come across.

Everything comes across

Every column is pulled on every run, including the ones that are always empty. The AI has to wade through all of them.

Doing it yourself

Every column comes across, every run

columns pulled0
of them empty or constant0
Only what holds data

Columns are checked for fill before they are kept. In this NetSuite example, 151 of 342 made the cut.

With

Columns profiled for fill; only the useful ones come across

columns checked0
columns kept0

03CleanCodes become names your team reads.

Codes in every report

ORD_TYP R, RGN 04, CHNL 07. Someone decodes them in each report, and each report decodes them a little differently.

Doing it yourself

Raw codes and exceptions, mapped by hand in every report

codes to decode0
reports that repeat the mapping0
Transformed as it loads

Columns get names your team reads, and functions run on each one while the table loads: trim and set the case of text, cast types, turn text into dates and numbers, and fill blanks. The original rows stay underneath.

With

Names your team reads, transformed as it loads

functions applied0
places it's done0

04ModelJoins set up once and checked, so totals stay true.

Joins that quietly multiply

Join on order number alone and two companies' orders collide. Add a style master with two rows per style and totals quadruple, with no error to warn you.

Doing it yourself

A missed key and a duplicated master quietly multiply rows

rows after joins0
net sales reported$1,480,560
Set up once, checked before it saves

How your systems relate is set up once, with you, and checked before it saves, so totals stay true.

With

Keys and masters handled once, checked before they save

rows after joins0
net sales reported$370,140

05DefineOne definition, used everywhere.

Three versions of net sales

Finance takes out returns, sales doesn't, ops leaves out samples. Each number is defensible, and none of them match.

Doing it yourself

Each team keeps its own version of "net sales"

versions in use0
spread between them$32,470
One definition everyone uses

Net sales is defined once and reused across dashboards, reports and questions.

With

One definition, reused by every board, report and answer

versions in use0
places that use it0

06TeachYour team's words, taught once.

A prompt that keeps growing

Each new word, like doors, sell-through or the West, gets pasted into a prompt. It keeps growing and still misses the words nobody has added.

Doing it yourself

A prompt that grows every time someone uses a new word

prompt length (words)0
words still unknown0
Taught once, for the whole team

Teach a term once: what it means and what people call it. Words it can't place land in a review queue.

With

Teach each term once; your whole team can use it

terms taught0
waiting for review0

07RunPrepared ahead of time, not rebuilt on every question.

Rebuilt on every question

Every question pulls, joins and cleans from scratch, for every person who asks. A complex question can take many tool calls across several systems before an answer comes back.

Doing it yourself

Nothing is prepared. Every question pulls, joins and cleans from scratch

prep runs today0
systems queried per questionup to 5
Prepared ahead of time

Data is prepared in a batch run, so questions read data that is already joined and cleaned.

With

Prepared once in a batch, ready for every question and every person

prep runs today0
systems queried per question0

08ServeAnswers come from MerchantsBI, not your live ERP.

A working day for a team of eight, sped up · illustration08:00
Your ERP takes the load

Every dashboard click and question becomes a query on your live ERP, competing with the people running the business on it.

Reporting straight off the ERP

Every person's question is a query on your ERP

FinanceSalesBuyingOpsE-comOwnerPlanningStores
0 people asking right now
Your ERP
0 queries at once
questions0
queries on your ERP0
ERP load from reporting
Your ERP stays out of it

Dashboards, reports and questions run on MerchantsBI's copy of your data. Your ERP is read in batches.

With

Everyone asks MerchantsBI. Your ERP is read in batches

FinanceSalesBuyingOpsE-comOwnerPlanningStores
0 people asking right now
Your ERP
0 queries at once
questions0
queries on your ERP0
ERP load from reporting
1 / 8
  • NetSuite
  • Walmart
  • BigCommerce
  • Wix
  • Lightspeed
  • QuickBooks
  • PayPal
  • Odoo
  • HubSpot
  • Meta Ads
  • BigQuery
  • SQL Server
  • Google Drive
  • Shopify
  • eBay
  • WooCommerce
  • Square
  • ShipStation
  • Xero
  • SAP Business One
  • Oracle
  • Klaviyo
  • Google Analytics
  • PostgreSQL
  • MongoDB
  • Box
  • Amazon
  • TikTok Shop
  • Magento
  • Clover
  • SPS Commerce
  • Stripe
  • Dynamics 365
  • Salesforce
  • Mailchimp
  • Snowflake
  • MySQL
  • Dropbox
  • Excel & CSV

The weekly report gets done. Then the next question arrives.

If you sell in stores, online and wholesale, your numbers live in separate systems. Someone on your team turns them into answers: the ops manager, the analyst, finance.

Every new question, like why margin dropped in the West, starts over. With spreadsheets, someone exports, combines and checks again while the decision waits. With AI connected to each system, every question means minutes of paging through raw records, matching products across systems and working out the formula again, for every person who asks.

Either way, the work behind one answer doesn't carry over to the next.

MerchantsBI helps your team answer the next question without starting over.

  1. Ownerasked

    “Why did margin drop in the West?”

    Export from 3 systemsRebuild the spreadsheetCheck against finance
    AI chat with your exports · example
    ▸ Read 3 files: sales_export.xlsx, pos_oct.csv, erp_costs.csv

    Gross margin in the West fell 3.3 points in October, to 37.9%. Most of the drop came from wholesale, where two accounts got deeper discounts.

    ChannelSeptOct
    Wholesale38.4%32.3%
    Retail stores44.1%42.1%
    Online46.0%45.2%
    AI chat with MCP connectors · example
    ▸ Used Shopify, POS and NetSuite tools · 11 calls

    Gross margin in the West fell 3.3 points in October, to 37.9%. Most of the drop came from wholesale, where two accounts got deeper discounts.

    ChannelSeptOct
    Wholesale38.4%32.3%
    Retail stores44.1%42.1%
    Online46.0%45.2%
    MerchantsAIexample answer · invented numbers
    ▾ HOW WE GOT THISratio Gross Margin %by Channelwhere Region is Westwhen Oct vs Sep
    ▾ SUMMARY

    Gross margin in the West fell 3.3 points in October, to 37.9%. Most of the drop came from wholesale, where two accounts got deeper discounts.

    Margin change (pts)
    Wholesale-6.1
    Retail stores-2.0
    Online-0.8
    Is that wholesale or our own stores?Which accounts?
  2. Financeasked

    “Is that wholesale or our own stores?”

    Export from 3 systemsRebuild the spreadsheetCheck against finance
    AI chat with your exports · example
    ▸ Read 3 files: sales_export.xlsx, pos_oct.csv, erp_costs.csv

    Wholesale explains about 71% of the drop; your own stores about 22%. Online is a small part of it.

    ChannelShare of the drop
    Wholesale71%
    Retail stores22%
    Online7%
    AI chat with MCP connectors · example
    ▸ Used Shopify, POS and NetSuite tools · 7 calls

    Wholesale explains about 71% of the drop; your own stores about 22%. Online is a small part of it.

    ChannelShare of the drop
    Wholesale71%
    Retail stores22%
    Online7%
    MerchantsAIexample answer · invented numbers
    ▾ HOW WE GOT THISshare of Margin Changeby Channelwhere Region is West
    ▾ SUMMARY

    Wholesale explains about 71% of the drop; your own stores about 22%. Online is a small part of it.

    Share of the drop
    Wholesale71%
    Retail stores22%
    Online7%
    Which wholesale accounts?Show by store
  3. Buyingasked

    “What was sell-through last month, across all channels?”

    Export from 3 systemsRebuild the spreadsheetCheck against finance
    AI chat with your exports · example
    ▸ Read 3 files: orders_oct.csv, pos_oct.csv, inventory_receipts.xlsx

    Sell-through for October was 48.1% across all channels, down from 51.6% in September. Retail stores are pulling the total down: the most inventory and the lowest rate.

    ChannelUnits soldUnits availableSell-through
    Online store4,8209,60050.2%
    Retail stores6,15014,30043.0%
    Wholesale2,4003,90061.5%
    Total13,37027,80048.1%

    I calculated sell-through as units sold ÷ (beginning inventory + units received). Let me know if you count returns differently.

    AI chat with MCP connectors · example
    ▸ Used Shopify, POS and NetSuite tools · 12 calls

    Sell-through for October was 48.1% across all channels, down from 51.6% in September. Retail stores are pulling the total down: the most inventory and the lowest rate.

    ChannelUnits soldUnits availableSell-through
    Online store4,8209,60050.2%
    Retail stores6,15014,30043.0%
    Wholesale2,4003,90061.5%
    Total13,37027,80048.1%

    I calculated sell-through as units sold ÷ (beginning inventory + units received). Let me know if you count returns differently.

    MerchantsAIexample answer · invented numbers
    ▾ HOW WE GOT THISratio Sell-Throughby Channelwhen last monthfrom Sales + Inventory + Receipts4 rows
    ▾ SUMMARY

    Sell-through for October was 48.1% across all channels, down from 51.6% in September. Retail stores are pulling the total down: they carry the most inventory and had the lowest rate.

    HOW I READ IT
    • Units sold ÷ (beginning inventory + units received), net of returns, using your definition of Sell-Through.
    Sell-through by channel
    Wholesale61.5%
    Online store50.2%
    Retail stores43.0%
    ▾ TABLE
    👁ChannelUnits SoldUnits AvailableSell-Through
    1Online store4,8209,60050.2%
    2Retail stores6,15014,30043.0%
    3Wholesale2,4003,90061.5%
    4Total13,37027,80048.1%
    Which categories are dragging it down?Break retail down by storeCompare to last October
  4. Buyingasked

    “Which categories are dragging it down?”

    Export from 3 systemsRebuild the spreadsheetCheck against finance
    AI chat with your exports · example
    ▸ Read 3 files: orders_oct.csv, pos_oct.csv, inventory_receipts.xlsx

    Running and Trail are dragging retail sell-through down; Apparel is above average. Running carries the most retail inventory.

    CategorySell-through
    Running39.0%
    Trail41.5%
    Lifestyle46.2%
    Apparel52.8%

    Using the same sell-through formula as before.

    AI chat with MCP connectors · example
    ▸ Used Shopify, POS and NetSuite tools · 9 calls

    Running and Trail are dragging retail sell-through down; Apparel is above average. Running carries the most retail inventory.

    CategorySell-through
    Running39.0%
    Trail41.5%
    Lifestyle46.2%
    Apparel52.8%

    Using the same sell-through formula as before.

    MerchantsAIexample answer · invented numbers
    ▾ HOW WE GOT THISratio Sell-Throughby Categorywhere Channel is Retail storeswhen last month
    ▾ SUMMARY

    Running and Trail are dragging retail sell-through down; Apparel is above average. Running carries the most retail inventory.

    Sell-through, retail stores
    Running39%
    Trail41.5%
    Lifestyle46.2%
    Apparel52.8%
    Which stores?Compare to last October
  5. E-comasked

    “Did the Amazon promo pull sales from our site?”

    Export from 3 systemsRebuild the spreadsheetCheck against finance
    AI chat with your exports · example
    ▸ Read 2 files: shopify_weekly.csv, amazon_weekly.csv

    Site sales dipped 6% during the Amazon promo week and recovered the week after. No lasting shift from your site to Amazon.

    Week ofSite salesAmazon sales
    Oct 6$182k$96k
    Oct 13 (promo)$171k$148k
    Oct 20$185k$101k
    AI chat with MCP connectors · example
    ▸ Used Shopify and Amazon tools · 8 calls

    Site sales dipped 6% during the Amazon promo week and recovered the week after. No lasting shift from your site to Amazon.

    Week ofSite salesAmazon sales
    Oct 6$182k$96k
    Oct 13 (promo)$171k$148k
    Oct 20$185k$101k
    MerchantsAIexample answer · invented numbers
    ▾ HOW WE GOT THISsum of Net Salesby Weekby Channelwhen Oct 6 to Oct 26
    ▾ SUMMARY

    Site sales dipped 6% during the Amazon promo week and recovered the week after. No lasting shift from your site to Amazon.

    Site sales by week ($k)
    Oct 6182
    Oct 13171
    Oct 20185
    Did the promo bring new customers?Margin on promo orders
 

AI is only part of the picture. Your team still needs great reporting.

Connect. Connect your systems in a few clicks and see every table they hold.

Build action plans. Turn raw tables into clean, joined, report-ready data with step-by-step action plans.

Schedule. Decide when each system refreshes, from hourly to nightly, inside the hours you allow.

Sync. Watch every sync land, system by system and table by table, with row counts and times.

Navigation. Arrange the pages each team sees and how each one opens.

Model relationships. Define how your tables join, once, and check every join before it goes live.

Data tagging. Teach MerchantsAI the words your team uses for every column and code.

Formula builder. Write a measure once, like net sales or sell-through, and use it everywhere.

Dashboards. Give every team a live board where one filter updates every tile.

Reports. Build pivot reports by dragging fields, then format, drill into and export them.

MerchantsAI. Ask a question in plain language and get the answer, the chart and the table behind it.

Scheduled reports. Send saved reports to the right people on a schedule, as Excel or CSV.

Alerts. Coming soon: get told when a number moves, with the rows behind it.

01Ingest & Transform
02Design & Model
03Visualize
04Schedule & Alert
Search connectors
NSNetSuite
Shopify
Amazon
Walmart
QuickBooks
Square
BigCommerce
Salesforce
Snowflake
Dropbox
Stripe
SPSSPS Commerce
eBay
WooCommerce
LSLightspeed
D365Dynamics 365
Xero
HubSpot
SSShipStation
Google Analytics
PostgreSQL
Connect · NetSuite
Account ID
TSTDRV2481193
Token
••••••••••••••••
Testing connection…✓ Connected · 214 tables found
  • Sales Orders412,880 rows
  • Items18,240 rows
  • Customers6,912 rows
  • Inventory Balances96,404 rows
  • Purchase Orders24,118 rows
  • Item Receipts31,560 rows
  • Locations48 rows
Build Sales Order LinesHide run▶{ }×
✦ GeneratePulls NetSuite sales orders, joins items and customers, maps status codes, loads the model.
⋮⋮ReadyCreate Sales Order LinesPreview TableMap Metadata↺ Reset Table
✓Table✓Method3Source4Ingest5Columns6Filter7Review8Done

Source Selection

#1Left Tablesales_ordersTypeLeftJoin Tableitems
Join Conditions
item_id=item_id×
+ Add Condition✓ Many-to-One (N:1)
#2Left Tablesales_ordersTypeLeftJoin Tablecustomers
Join Conditions
customer_id=customer_id×
subsidiary=subsidiary×
+ Add Condition✓ Many-to-One (N:1)
+ Add JoinValidate JoinsCollapse All

Column Mapping

Source profiled 9 Nov 14:02 · 412,880 rows · 151 columns have values · 191 are empty Re-profile

Available Columns - 196 total
Filter... (src:, type: or fill:)
Has valuesSparse (under 1%)Empty
ship_via0%⋮memo<0.1%⋮legacy_ref0%⋮promo_code3%⋮fax0%⋮status_cd100%Text⋮
Included Columns - 6 total
+ Add Custom Column
PKorder_no100%Text⋮item_id100%Text⋮customer_id100%Text⋮order_date100%Date⋮quantity99%Number⋮net_amount98%Number⋮Status NamefxText⋮

Review Summary

  • Create Table:sales_order_lines
  • Destination:MerchantsBI warehouse
  • Ingestion Strategy:incremental-value · order_date
  • Joins:items (Left, N:1) · customers (Left, N:1)
  • Mapped Columns:order_no → order_nonet_amount → net_salesstatus_cd → status_name (fx)+7
  • Primary Key Columns:order_noline_id
  • Global Source Filters:order_date ≥ 2023-01-01 AND status ≠ 'Cancelled'
Finalize Plan
⋮⋮ReadySet Primary KeysSQL Script▸
⋮⋮ReadyUpdate Records · map return codesAction Plan▸
+
SaveSave & Close
Run
Not runChoose a run ▾
  • Create Sales Order Lines
  • Set Primary Keys
  • Update Records
All 3 actions in this run
Sync schedule · NetSuite
How often
HourlyEvery 2 hoursDailyWeeklyMonthly
Run times
06:0008:0010:0012:0014:0016:0018:00
Days
MTWTFSS
Only between
05:00 – 20:00
Recent runs
  • 08:00412,880 rows · complete
  • 06:00411,906 rows · complete
  • Fri 18:00410,772 rows · complete
  • Fri 16:00410,210 rows · complete
Next run: today 10:00 · then 12:00
Data syncs5 integrations · 20 tables · 12 filesSyncing NetSuite…
  • ▾ NetSuiteEvery 2 hours8 tables1,874,372 rows✓ 08:00
    • Sales Orders412,880 rows✓ 08:00
    • Sales Order Lines1,284,210 rows✓ 08:01
    • Items18,240 rows✓ 08:02
    • Customers6,912 rows✓ 08:03
    • Inventory Balances96,404 rows✓ 08:04
    • Purchase Orders24,118 rows✓ 08:05
    • Item Receipts31,560 rows✓ 08:06
    • Locations48 rows✓ 08:07
  • ▸ ShopifyEvery hour4 tables96,140 rows✓ 09:00
  • ▸ POSNightly3 tables58,310 rows✓ 02:00
  • ▸ AmazonEvery 4 hours5 tables71,902 rows✓ 08:00
  • ▸ Dropbox CSVDaily12 files12 files✓ 06:00
Drag to arrange the left rail. Groups hold pages.No unsaved changesDiscardSave changes
✓ Saved. Your navigation is live. Built 6 filter fields and 12 report columns for the new page.
Your navigation14 items+ Page▣ Group
  • ⋮⋮▾▣Sales
  • ⋮⋮○Overview
  • ⋮⋮○By Channel
  • ⋮⋮○By Account
  • ⋮⋮▾▣Inventory
  • ⋮⋮○Stock on HandAuto
  • ⋮⋮○Open POs
  • ⋮⋮○Sell-ThroughSetup
  • ⋮⋮▸▣Finance3
  • ⋮⋮▾▣Leadership
  • ⋮⋮○Executive Overview
  • ⋮⋮○Weekly ScorecardHidden
Drop here to move to the end of the top level
○By Channel
What is this?
GroupReportDashboard

A report page is built on one activated table.

Icon
○ Change
Name
By Channel
Report shell
Sales Order Lines Locked
Timeframe dropdownChanged
Date field · Order Date ▾
Total row
Visible in the navigation
  • ✓ Has a name
  • ✓ Built on sales
Fields12 of 48 shown
Search 48 fields…All tables · 48 ▾All types ▾Only included · 12
Sales8 fieldsOpens expanded
⋮⋮
Net Salessales.net_amount
NumberUSD
⋮⋮
Unitssales.quantity
NumberFormat
TotalsSum ▾Use as measure✓PinLeft ▾GroupSales
⋮⋮
Margin %sales.margin_pct · via formula
NumberPercent
⋮⋮
Order Datesales.order_date
DateMMM d, yyyy
⋮⋮
Channelcustomers.channel · via customer_id
TextFormat
⋮⋮
Returnedsales.is_return
Yes/NoFormat
Before this goes live
⚠Sell-Through needs a report shell before it can go live.Repair

Every relationship your reports join through.

Default — 7 tables · 5 joins ▾ + Grouping ◇ Model☰ List No unsaved relationships Discard Save relationships
✓ Saved. Your model is live.
Default5 relationships + RelationshipClick a tableFit
sales_order_linesFACT · 3 out
inventory_balancesFACT · 2 out
customers1 in · 0 out
items2 in · 0 out
locations2 in · 0 out
calendar0 in · 0 out
returns_lognot in the modelnothing joins to it
relationshipselectedfailed validation switched offcalendar factdimensionnot in the model
Selected relationshipNot saved yet

Select a relationship on the left to inspect it.

sales_order_lines
→
items
sales_order_lines=items
item_id=id✕
No join columns — nothing can join without them.

Columns pair row by row.

+ Column pair
Match on date only
✓

many-to-one — safe for totals

Check
In use
42described 36Footwear words · 6 to do 18values named 3unexplained 2your definitions 64hydrated · 12,480 values
No unsaved changes DiscardSave
Search columns, tags and values… Described 42Suggested 5Blank 31
sales_order_lines9 described · 24 columnsSales · main
net_amount
net salesrevenueadd tag
Order line amount after discountsMeasure⋯
chnl_cd
channeladd tag
Sales channel codeGroup by⋯
✓Filter by value4 values · 412,880 rows
  • 07198,18248%
  • 03127,99331%online = 03
  • 1170,19017%stores = 11
  • 0516,5154%
what people call it…Add
ord_typ
order typeadd tag
Kind of order: sale, return or samplesuggested AcceptDismiss
ship_dt
what do you call it?
describe this column…⋯
qty_shipped
units shippedunitsadd tag
Units that left the warehouseMeasure⋯
legacy_ref
what do you call it?
describe this column…⋯
▦New report formula×
Static ValueDynamic Formula
Search functions...
  • COLUMNS
  • Net Amountsales.net_amount
  • Order Typesales.order_type
  • Quantitysales.quantity
  • Unit Pricesales.unit_price
  • Order Datesales.order_date
  • OPERATORS
  • +Add
  • -Subtract
  • *Multiply
  • /Divide
  • ( )Group
  • ||Concat
  • STRING FUNCTIONS
  • UPPERUpper case
  • TRIMRemove spaces
  • REPLACESwap text
  • COALESCEHandle NULLs
  • MATH & DATE
  • ROUNDRound a number
  • ABSAbsolute value
  • YEARYear of a date
  • DAYS BETWEENGap in days
  • LOGIC
  • CASEConditional Logic
  • ANDBoth true
  • OREither true
SQL ExpressionClear
Use standard SQL syntax. Click items on the left to insert.
functioncolumnoperatorkeywordtextnumberunknown
Validate Formula✓ ValidApply Formula
File ▾ Executive Overview ✓ ▾ Timeframe · Q3 ▾ region: West × + Add filter Capacity 14 / 18 ● Editing Done
Gross sales$1.24M▲ 12.4% vs LY
Units sold86.2K▲ 8.1% vs LY
Gross margin41.2%▼ 0.8 pts vs LY
Sell-through48.1%▼ 3.5 pts vs LY
Net sales by region click a bar to filter
West$412K
East$388K
Central$251K
South$189K
Gross sales · this year vs last weekly
This yearLast year
4 × 2
Margin % by category
JulAugSep
Running44%43%41%
Trail38%33%31%
Lifestyle39%40%38%
Apparel16%14%15%
Top styles
  • Pegasus 41104,220
  • Vomero 1868,940
  • Structure 2662,410
  • Trail Ridge 358,120
  • Summit Knit44,860
Chart type
BarColumnLineAreaPieDonutScatterBubbleRadial barSunburstTreemapRadial gaugeLinear gauge
Drill · Units soldregion: West×
OrderDateStyleChannelStoreUnits
SO-48211Sep 28Pegasus 41RetailDenver24
SO-48207Sep 28Vomero 18Online—2
SO-48190Sep 27Structure 26Wholesale—180
SO-48176Sep 27Trail Ridge 3RetailBoulder11
SO-48162Sep 26Pegasus 41Amazon—36
SO-48151Sep 26Summit KnitRetailAustin8
Showing the order lines behind 28.9K unitsExport ▾
Margin by Category ▾ Show by ▾ Timeframe ▾ region: West × 1margin ↓ × + Add filterExport ▾Conditional formatting
2025 · Q22025 · Q3
CategorySalesSales
▸ Footwear412,180455,020
▸ Apparel206,340231,510
Total618,520686,530
Σ Total2 groups · page 1 of 1
Columns×
ColumnsPivotFilterPivot Columns
Search fields
  • ⋮⋮CategoryAbc
  • ⋮⋮Sub-categoryAbc
  • ⋮⋮StyleAbc
  • ⋮⋮Order Datedate
  • ⋮⋮Units123
fxSearch formulas+
  • Measures · drag into Values
  • ⋮⋮Margin %fx
Columnsclear
Order Date · Quarter×
Rowsclear
Category×
Sub-category×
Style×
Valuesclear
Sum of Net Sales ▾×
Sum of Units ▾×
Average of Margin % ▾×
GroupsCol total · RightCol subRow subUpdate
Conditional Formatting×
New Rule
RowCellColumn
Margin %
Less Than25
Active Rules
Margin % ≥ 40 · greenMargin % 25–40 · amberMargin % < 25 · red
Drill · Vomero 18 · 2025 Q3 · Sales×
OrderDateCustomerChannelUnitsNet sales
SO-47702Sep 24Harbor StrideWholesale240$6,912
SO-47688Sep 23Online storeOnline3$420
SO-47651Sep 22Denver storeRetail18$2,394
SO-47630Sep 21AmazonAmazon41$5,084
SO-47609Sep 20Ridgeline Run Co.Wholesale120$3,456
The order lines behind $68,940Export ▾
Excel Styled + brandedCSV
✓ Margin by Category.xlsx is ready
Why did margin drop in the West?
Working on itReading your questionFinding the right tablesRunning the numbersWriting the answer
MerchantsAIexample answer · invented numbers
▾ HOW WE GOT THISratio Gross Margin %by Channelwhere Region is Westwhen Oct vs Sep
▾ SUMMARY

Gross margin in the West fell 3.3 points in October, to 37.9%. Most of the drop came from wholesale, where two accounts got deeper discounts.

Margin change (pts)
Wholesale-6.1
Retail stores-2.0
Online-0.8
Is that wholesale or our own stores?Which accounts?
Is that wholesale or our own stores?
Working on itReading your questionFinding the right tablesRunning the numbersWriting the answer
MerchantsAIexample answer · invented numbers
▾ HOW WE GOT THISshare of Margin Changeby Channelwhere Region is West
▾ SUMMARY

Wholesale explains about 71% of the drop; your own stores about 22%. Online is a small part of it.

Share of the drop
Wholesale71%
Retail stores22%
Online7%
Which wholesale accounts?Show by store
What was sell-through last month, across all channels?
Working on itReading your questionFinding the right tablesRunning the numbersWriting the answer
MerchantsAIexample answer · invented numbers
▾ HOW WE GOT THISratio Sell-Throughby Channelwhen last monthfrom Sales + Inventory + Receipts4 rows
▾ SUMMARY

Sell-through for October was 48.1% across all channels, down from 51.6% in September. Retail stores are pulling the total down: they carry the most inventory and had the lowest rate.

HOW I READ IT
  • Units sold ÷ (beginning inventory + units received), net of returns, using your definition of Sell-Through.
Sell-through by channel
Wholesale61.5%
Online store50.2%
Retail stores43.0%
▾ TABLE
👁ChannelUnits SoldUnits AvailableSell-Through
1Online store4,8209,60050.2%
2Retail stores6,15014,30043.0%
3Wholesale2,4003,90061.5%
4Total13,37027,80048.1%
Which categories are dragging it down?Break retail down by storeCompare to last October
Which categories are dragging it down?
Working on itReading your questionFinding the right tablesRunning the numbersWriting the answer
MerchantsAIexample answer · invented numbers
▾ HOW WE GOT THISratio Sell-Throughby Categorywhere Channel is Retail storeswhen last month
▾ SUMMARY

Running and Trail are dragging retail sell-through down; Apparel is above average. Running carries the most retail inventory.

Sell-through, retail stores
Running39%
Trail41.5%
Lifestyle46.2%
Apparel52.8%
Which stores?Compare to last October
Ask MerchantsAI…➤
  • Weekly sales by channelMondays · 7:00 AM · Excel · 4 people
  • Open POs by styleEvery weekday · 6:30 AM · CSV · Buying
  • Month-end margin1st of the month · 8:00 AM · Excel · Finance
  • Store sell-throughMondays · 8:00 AM · Excel · Retail ops
  • Amazon top stylesFridays · 4:00 PM · CSV · E-com
  • Wholesale open ordersEvery weekday · 7:30 AM · Excel · Sales
Next send: Mon 7:00 AM · Weekly sales by channel
New alertConcept · coming soon
WhenSell-Throughforany styleinRetail stores drops below40%or falls more than5 ptsvsthe last 4 weeks
CheckEvery morning · 7:00
TellBuying teamRetail ops
ByEmailIn the app
IncludeThe rows that tripped itA MerchantsAI summary
Test against last monthWould have fired 3 times · Vomero 18, Ridge Jacket, Tempo ShortSave alert
Alerts3 today
  • !
    Sell-through fell to 34% · Vomero 18Retail stores · down 9 pts vs the last 4 weeks · 7:00 AM
    Ask MerchantsAI why ▸Open report ▸
  • !
    Pegasus 41 covers 2.1 weeks of salesThe next PO lands in 3 weeks · Amazon · 7:00 AM
    See open POs ▸
  • ▲
    Amazon sales up 22% vs last weekPromo week · all styles · Mon 7:00 AM
    Compare channels ▸
  • ✓
    Running margin back above 40%Cleared · West · Fri 7:00 AM
MerchantsBI MCP server

Already use Claude, ChatGPT or Grok? Connect it to MerchantsBI.

MCP is how an AI assistant reaches your data. MerchantsBI does the heavy lifting behind it: it brings your systems together, joins them, applies your formulas and permissions, and serves it all to your AI through one MCP connection.

  • Every system, one connection. NetSuite, Shopify, Amazon and the rest arrive already joined, instead of one connector per system.
  • Your formulas. Net sales, margin and sell-through mean what your team defined in MerchantsBI.
  • Your words. The tags your team taught MerchantsAI travel with the data, so "wholesale" means your wholesale.
  • Your permissions. Each person's AI sees only what that person can see in MerchantsBI.

Use MerchantsAI inside MerchantsBI, your own AI over MCP, or both. They work from the same model.

  • NetSuite
  • Shopify
  • Amazon
  • QuickBooks
  • Walmart
MCP server
  • Joined model
  • Your formulas
  • Your words
  • Your access
  • Claude
  • ChatGPT & Codex
  • Grok
  • Gemini
  • Your own agent

See what MerchantsBI can do with your data.

Bring your systems together, ask the next question, and get an answer your whole team can work from.